5 files changed, 776 insertions, 72 deletions

diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile
index 3b9e5464b5b3..afc4aed9231a 100644
--- a/arch/arm64/kvm/hyp/vhe/Makefile
+++ b/arch/arm64/kvm/hyp/vhe/Makefile
@@ -6,6 +6,8 @@
 asflags-y := -D__KVM_VHE_HYPERVISOR__
 ccflags-y := -D__KVM_VHE_HYPERVISOR__
 
+CFLAGS_switch.o += -Wno-override-init
+
 obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o
 obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \
 	 ../fpsimd.o ../hyp-entry.o ../exception.o
diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c
index 289689b2682d..0100339b09e0 100644
--- a/arch/arm64/kvm/hyp/vhe/debug-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c
@@ -19,8 +19,3 @@ void __debug_switch_to_host(struct kvm_vcpu *vcpu)
 {
 	__debug_switch_to_host_common(vcpu);
 }
-
-u64 __kvm_get_mdcr_el2(void)
-{
-	return read_sysreg(mdcr_el2);
-}
diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c
index 1581df6aec87..c9b330dc2066 100644
--- a/arch/arm64/kvm/hyp/vhe/switch.c
+++ b/arch/arm64/kvm/hyp/vhe/switch.c
@@ -33,36 +33,66 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data);
 DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt);
 DEFINE_PER_CPU(unsigned long, kvm_hyp_vector);
 
-static void __activate_traps(struct kvm_vcpu *vcpu)
+/*
+ * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1
+ * semantics, irrespective of the configuration), but that cannot be
+ * applied to the actual HW as things would otherwise break badly.
+ *
+ * - TGE: we want the guest to use EL1, which is incompatible with
+ *   this bit being set
+ *
+ * - API/APK: they are already accounted for by vcpu_load(), and can
+ *   only take effect across a load/put cycle (such as ERET)
+ */
+#define NV_HCR_GUEST_EXCLUDE	(HCR_TGE | HCR_API | HCR_APK)
+
+static u64 __compute_hcr(struct kvm_vcpu *vcpu)
 {
-	u64 val;
+	u64 guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2);
+	u64 hcr = vcpu->arch.hcr_el2;
 
-	___activate_traps(vcpu);
+	if (!vcpu_has_nv(vcpu))
+		return hcr;
 
-	if (has_cntpoff()) {
-		struct timer_map map;
+	/*
+	 * We rely on the invariant that a vcpu entered from HYP
+	 * context must also exit in the same context, as only an ERET
+	 * instruction can kick us out of it, and we obviously trap
+	 * that sucker. PSTATE.M will get fixed-up on exit.
+	 */
+	if (is_hyp_ctxt(vcpu)) {
+		host_data_set_flag(VCPU_IN_HYP_CONTEXT);
 
-		get_timer_map(vcpu, &map);
+		hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB;
 
-		/*
-		 * We're entrering the guest. Reload the correct
-		 * values from memory now that TGE is clear.
-		 */
-		if (map.direct_ptimer == vcpu_ptimer(vcpu))
-			val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
-		if (map.direct_ptimer == vcpu_hptimer(vcpu))
-			val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
+		if (!vcpu_el2_e2h_is_set(vcpu))
+			hcr |= HCR_NV1;
 
-		if (map.direct_ptimer) {
-			write_sysreg_el0(val, SYS_CNTP_CVAL);
-			isb();
+		write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2);
+	} else {
+		host_data_clear_flag(VCPU_IN_HYP_CONTEXT);
+
+		if (guest_hcr & HCR_NV) {
+			u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id()));
+
+			/* Inherit the low bits from the actual register */
+			va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0);
+			write_sysreg_s(va, SYS_VNCR_EL2);
+
+			/* Force NV2 in case the guest is forgetful... */
+			guest_hcr |= HCR_NV2;
 		}
 	}
 
-	val = read_sysreg(cpacr_el1);
-	val |= CPACR_ELx_TTA;
-	val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN |
-		 CPACR_EL1_SMEN_EL0EN | CPACR_EL1_SMEN_EL1EN);
+	BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) &&
+	       host_data_test_flag(L1_VNCR_MAPPED));
+
+	return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE);
+}
+
+static void __activate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	u64 cptr;
 
 	/*
 	 * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to
@@ -72,18 +102,102 @@ static void __activate_traps(struct kvm_vcpu *vcpu)
 	 * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM
 	 * shift value for trapping the AMU accesses.
 	 */
+	u64 val = CPACR_EL1_TTA | CPTR_EL2_TAM;
 
-	val |= CPTR_EL2_TAM;
-
-	if (guest_owns_fp_regs(vcpu)) {
+	if (guest_owns_fp_regs()) {
+		val |= CPACR_EL1_FPEN;
 		if (vcpu_has_sve(vcpu))
-			val |= CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN;
+			val |= CPACR_EL1_ZEN;
 	} else {
-		val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN);
 		__activate_traps_fpsimd32(vcpu);
 	}
 
+	if (!vcpu_has_nv(vcpu))
+		goto write;
+
+	/*
+	 * The architecture is a bit crap (what a surprise): an EL2 guest
+	 * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA,
+	 * as they are RES0 in the guest's view. To work around it, trap the
+	 * sucker using the very same bit it can't set...
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu))
+		val |= CPTR_EL2_TCPAC;
+
+	/*
+	 * Layer the guest hypervisor's trap configuration on top of our own if
+	 * we're in a nested context.
+	 */
+	if (is_hyp_ctxt(vcpu))
+		goto write;
+
+	cptr = vcpu_sanitised_cptr_el2(vcpu);
+
+	/*
+	 * Pay attention, there's some interesting detail here.
+	 *
+	 * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two
+	 * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest):
+	 *
+	 *  - CPTR_EL2.xEN = x0, traps are enabled
+	 *  - CPTR_EL2.xEN = x1, traps are disabled
+	 *
+	 * In other words, bit[0] determines if guest accesses trap or not. In
+	 * the interest of simplicity, clear the entire field if the guest
+	 * hypervisor has traps enabled to dispel any illusion of something more
+	 * complicated taking place.
+	 */
+	if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0)))
+		val &= ~CPACR_EL1_FPEN;
+	if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0)))
+		val &= ~CPACR_EL1_ZEN;
+
+	if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S2POE, IMP))
+		val |= cptr & CPACR_EL1_E0POE;
+
+	val |= cptr & CPTR_EL2_TCPAC;
+
+write:
 	write_sysreg(val, cpacr_el1);
+}
+
+static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val = CPACR_EL1_FPEN | CPACR_EL1_ZEN_EL1EN;
+
+	if (cpus_have_final_cap(ARM64_SME))
+		val |= CPACR_EL1_SMEN_EL1EN;
+
+	write_sysreg(val, cpacr_el1);
+}
+
+static void __activate_traps(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	___activate_traps(vcpu, __compute_hcr(vcpu));
+
+	if (has_cntpoff()) {
+		struct timer_map map;
+
+		get_timer_map(vcpu, &map);
+
+		/*
+		 * We're entrering the guest. Reload the correct
+		 * values from memory now that TGE is clear.
+		 */
+		if (map.direct_ptimer == vcpu_ptimer(vcpu))
+			val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		if (map.direct_ptimer == vcpu_hptimer(vcpu))
+			val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2);
+
+		if (map.direct_ptimer) {
+			write_sysreg_el0(val, SYS_CNTP_CVAL);
+			isb();
+		}
+	}
+
+	__activate_cptr_traps(vcpu);
 
 	write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1);
 }
@@ -95,7 +209,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 
 	___deactivate_traps(vcpu);
 
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
 
 	if (has_cntpoff()) {
 		struct timer_map map;
@@ -128,7 +242,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu)
 	 */
 	asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT));
 
-	kvm_reset_cptr_el2(vcpu);
+	__deactivate_cptr_traps(vcpu);
 
 	if (!arm64_kernel_unmapped_at_el0())
 		host_vectors = __this_cpu_read(this_cpu_vector);
@@ -162,6 +276,8 @@ static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu)
 
 void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu)
 {
+	host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu;
+
 	__vcpu_load_switch_sysregs(vcpu);
 	__vcpu_load_activate_traps(vcpu);
 	__load_stage2(vcpu->arch.hw_mmu, vcpu->arch.hw_mmu->arch);
@@ -171,33 +287,326 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu)
 {
 	__vcpu_put_deactivate_traps(vcpu);
 	__vcpu_put_switch_sysregs(vcpu);
+
+	host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL;
+}
+
+static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu,
+					 enum vcpu_sysreg reg)
+{
+	unsigned long ctl;
+	u64 cval, cnt;
+	bool stat;
+
+	switch (reg) {
+	case CNTP_CTL_EL0:
+		cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		ctl  = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0);
+		cnt  = compute_counter_value(vcpu_ptimer(vcpu));
+		break;
+	case CNTV_CTL_EL0:
+		cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		ctl  = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0);
+		cnt  = compute_counter_value(vcpu_vtimer(vcpu));
+		break;
+	default:
+		BUG();
+	}
+
+	stat = cval <= cnt;
+	__assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat);
+
+	return ctl;
+}
+
+static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr, val;
+
+	/*
+	 * Having FEAT_ECV allows for a better quality of timer emulation.
+	 * However, this comes at a huge cost in terms of traps. Try and
+	 * satisfy the reads from guest's hypervisor context without
+	 * returning to the kernel if we can.
+	 */
+	if (!is_hyp_ctxt(vcpu))
+		return false;
+
+	esr = kvm_vcpu_get_esr(vcpu);
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ)
+		return false;
+
+	switch (esr_sys64_to_sysreg(esr)) {
+	case SYS_CNTP_CTL_EL02:
+		val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
+		break;
+	case SYS_CNTP_CTL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTP_CTL);
+		else
+			val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0);
+		break;
+	case SYS_CNTP_CVAL_EL02:
+		val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		break;
+	case SYS_CNTP_CVAL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu)) {
+			val = read_sysreg_el0(SYS_CNTP_CVAL);
+
+			if (!has_cntpoff())
+				val -= timer_get_offset(vcpu_hptimer(vcpu));
+		} else {
+			val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0);
+		}
+		break;
+	case SYS_CNTPCT_EL0:
+	case SYS_CNTPCTSS_EL0:
+		val = compute_counter_value(vcpu_hptimer(vcpu));
+		break;
+	case SYS_CNTV_CTL_EL02:
+		val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
+		break;
+	case SYS_CNTV_CTL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTV_CTL);
+		else
+			val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0);
+		break;
+	case SYS_CNTV_CVAL_EL02:
+		val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		break;
+	case SYS_CNTV_CVAL_EL0:
+		if (vcpu_el2_e2h_is_set(vcpu))
+			val = read_sysreg_el0(SYS_CNTV_CVAL);
+		else
+			val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0);
+		break;
+	case SYS_CNTVCT_EL0:
+	case SYS_CNTVCTSS_EL0:
+		val = compute_counter_value(vcpu_hvtimer(vcpu));
+		break;
+	default:
+		return false;
+	}
+
+	vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val);
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	u64 spsr, elr, mode;
+
+	/*
+	 * Going through the whole put/load motions is a waste of time
+	 * if this is a VHE guest hypervisor returning to its own
+	 * userspace, or the hypervisor performing a local exception
+	 * return. No need to save/restore registers, no need to
+	 * switch S2 MMU. Just do the canonical ERET.
+	 *
+	 * Unless the trap has to be forwarded further down the line,
+	 * of course...
+	 */
+	if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) ||
+	    (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET))
+		return false;
+
+	spsr = read_sysreg_el1(SYS_SPSR);
+	mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT);
+
+	switch (mode) {
+	case PSR_MODE_EL0t:
+		if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)))
+			return false;
+		break;
+	case PSR_MODE_EL2t:
+		mode = PSR_MODE_EL1t;
+		break;
+	case PSR_MODE_EL2h:
+		mode = PSR_MODE_EL1h;
+		break;
+	default:
+		return false;
+	}
+
+	/* If ERETAx fails, take the slow path */
+	if (esr_iss_is_eretax(esr)) {
+		if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr)))
+			return false;
+	} else {
+		elr = read_sysreg_el1(SYS_ELR);
+	}
+
+	spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode;
+
+	write_sysreg_el2(spsr, SYS_SPSR);
+	write_sysreg_el2(elr, SYS_ELR);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	int ret = -EINVAL;
+	u32 instr;
+	u64 val;
+
+	/*
+	 * Ideally, we would never trap on EL2 S1 TLB invalidations using
+	 * the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}.
+	 * But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2,
+	 * meaning that we can't track changes to the virtual TGE bit. So we
+	 * have to leave HCR_EL2.TTLB set on the host. Oopsie...
+	 *
+	 * Try and handle these invalidation as quickly as possible, without
+	 * fully exiting. Note that we don't need to consider any forwarding
+	 * here, as having E2H+TGE set is the very definition of being
+	 * InHost.
+	 *
+	 * For the lesser hypervisors out there that have failed to get on
+	 * with the VHE program, we can also handle the nVHE style of EL2
+	 * invalidation.
+	 */
+	if (!(is_hyp_ctxt(vcpu)))
+		return false;
+
+	instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+	val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu));
+
+	if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) &&
+	     vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) ||
+	    kvm_supported_tlbi_s1e2_op (vcpu, instr))
+		ret = __kvm_tlbi_s1e2(NULL, val, instr);
+
+	if (ret)
+		return false;
+
+	/*
+	 * If we have to check for any VNCR mapping being invalidated,
+	 * go back to the slow path for further processing.
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) &&
+	    atomic_read(&vcpu->kvm->arch.vncr_map_count))
+		return false;
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 esr = kvm_vcpu_get_esr(vcpu);
+	int rt;
+
+	if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1)
+		return false;
+
+	rt = kvm_vcpu_sys_get_rt(vcpu);
+
+	if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) {
+		vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2));
+	} else {
+		vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2);
+		__activate_cptr_traps(vcpu);
+	}
+
+	__kvm_skip_instr(vcpu);
+
+	return true;
+}
+
+static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu));
+
+	if (!vcpu_has_nv(vcpu))
+		return false;
+
+	if (sysreg != SYS_ZCR_EL2)
+		return false;
+
+	if (guest_owns_fp_regs())
+		return false;
+
+	/*
+	 * ZCR_EL2 traps are handled in the slow path, with the expectation
+	 * that the guest's FP context has already been loaded onto the CPU.
+	 *
+	 * Load the guest's FP context and unconditionally forward to the
+	 * slow path for handling (i.e. return false).
+	 */
+	kvm_hyp_handle_fpsimd(vcpu, exit_code);
+	return false;
+}
+
+static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_timer(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code))
+		return true;
+
+	if (kvm_hyp_handle_zcr_el2(vcpu, exit_code))
+		return true;
+
+	return kvm_hyp_handle_sysreg(vcpu, exit_code);
+}
+
+static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code)
+{
+	u64 iss;
+
+	if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS))
+		return false;
+
+	/*
+	 * Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2
+	 * is populated with a correct ISS for a sysreg trap. These fruity
+	 * parts are 64bit only, so unconditionally set IL.
+	 */
+	iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2));
+	vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) |
+				   FIELD_PREP(ESR_ELx_ISS_MASK, iss) |
+				   ESR_ELx_IL;
+	return false;
 }
 
 static const exit_handler_fn hyp_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]		= NULL,
 	[ESR_ELx_EC_CP15_32]		= kvm_hyp_handle_cp15_32,
-	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg,
+	[ESR_ELx_EC_SYS64]		= kvm_hyp_handle_sysreg_vhe,
 	[ESR_ELx_EC_SVE]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_FP_ASIMD]		= kvm_hyp_handle_fpsimd,
 	[ESR_ELx_EC_IABT_LOW]		= kvm_hyp_handle_iabt_low,
 	[ESR_ELx_EC_DABT_LOW]		= kvm_hyp_handle_dabt_low,
 	[ESR_ELx_EC_WATCHPT_LOW]	= kvm_hyp_handle_watchpt_low,
-	[ESR_ELx_EC_PAC]		= kvm_hyp_handle_ptrauth,
+	[ESR_ELx_EC_ERET]		= kvm_hyp_handle_eret,
 	[ESR_ELx_EC_MOPS]		= kvm_hyp_handle_mops,
+
+	/* Apple shenanigans */
+	[0x3F]				= kvm_hyp_handle_impdef,
 };
 
-static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu)
+static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code)
 {
-	return hyp_exit_handlers;
-}
+	synchronize_vcpu_pstate(vcpu, exit_code);
 
-static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
-{
 	/*
 	 * If we were in HYP context on entry, adjust the PSTATE view
-	 * so that the usual helpers work correctly.
+	 * so that the usual helpers work correctly. This enforces our
+	 * invariant that the guest's HYP context status is preserved
+	 * across a run.
 	 */
-	if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) {
+	if (vcpu_has_nv(vcpu) &&
+	    unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) {
 		u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT);
 
 		switch (mode) {
@@ -212,6 +621,12 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code)
 		*vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT);
 		*vcpu_cpsr(vcpu) |= mode;
 	}
+
+	/* Apply extreme paranoia! */
+	BUG_ON(vcpu_has_nv(vcpu) &&
+	       !!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu));
+
+	return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers);
 }
 
 /* Switch to the guest for VHE systems running in EL2 */
@@ -221,12 +636,13 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *guest_ctxt;
 	u64 exit_code;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
-	host_ctxt->__hyp_running_vcpu = vcpu;
+	host_ctxt = host_data_ptr(host_ctxt);
 	guest_ctxt = &vcpu->arch.ctxt;
 
 	sysreg_save_host_state_vhe(host_ctxt);
 
+	fpsimd_lazy_switch_to_guest(vcpu);
+
 	/*
 	 * Note that ARM erratum 1165522 requires us to configure both stage 1
 	 * and stage 2 translation for the guest context before we clear
@@ -240,11 +656,6 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 	sysreg_restore_guest_state_vhe(guest_ctxt);
 	__debug_switch_to_guest(vcpu);
 
-	if (is_hyp_ctxt(vcpu))
-		vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT);
-	else
-		vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT);
-
 	do {
 		/* Jump in the fire! */
 		exit_code = __guest_enter(vcpu);
@@ -256,9 +667,11 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)
 
 	__deactivate_traps(vcpu);
 
+	fpsimd_lazy_switch_to_host(vcpu);
+
 	sysreg_restore_host_state_vhe(host_ctxt);
 
-	if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)
+	if (guest_owns_fp_regs())
 		__fpsimd_save_fpexc32(vcpu);
 
 	__debug_switch_to_host(vcpu);
@@ -301,12 +714,12 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static void __hyp_call_panic(u64 spsr, u64 elr, u64 par)
+static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par)
 {
 	struct kvm_cpu_context *host_ctxt;
 	struct kvm_vcpu *vcpu;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	vcpu = host_ctxt->__hyp_running_vcpu;
 
 	__deactivate_traps(vcpu);
@@ -326,7 +739,6 @@ void __noreturn hyp_panic(void)
 	u64 par = read_sysreg_par();
 
 	__hyp_call_panic(spsr, elr, par);
-	unreachable();
 }
 
 asmlinkage void kvm_unexpected_el2_exception(void)
diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
index a8b9ea496706..3814b0b2c937 100644
--- a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
+++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c
@@ -15,6 +15,132 @@
 #include <asm/kvm_hyp.h>
 #include <asm/kvm_nested.h>
 
+static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu)
+{
+	/* These registers are common with EL1 */
+	__vcpu_sys_reg(vcpu, PAR_EL1)	= read_sysreg(par_el1);
+	__vcpu_sys_reg(vcpu, TPIDR_EL1)	= read_sysreg(tpidr_el1);
+
+	__vcpu_sys_reg(vcpu, ESR_EL2)	= read_sysreg_el1(SYS_ESR);
+	__vcpu_sys_reg(vcpu, AFSR0_EL2)	= read_sysreg_el1(SYS_AFSR0);
+	__vcpu_sys_reg(vcpu, AFSR1_EL2)	= read_sysreg_el1(SYS_AFSR1);
+	__vcpu_sys_reg(vcpu, FAR_EL2)	= read_sysreg_el1(SYS_FAR);
+	__vcpu_sys_reg(vcpu, MAIR_EL2)	= read_sysreg_el1(SYS_MAIR);
+	__vcpu_sys_reg(vcpu, VBAR_EL2)	= read_sysreg_el1(SYS_VBAR);
+	__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2) = read_sysreg_el1(SYS_CONTEXTIDR);
+	__vcpu_sys_reg(vcpu, AMAIR_EL2)	= read_sysreg_el1(SYS_AMAIR);
+
+	/*
+	 * In VHE mode those registers are compatible between EL1 and EL2,
+	 * and the guest uses the _EL1 versions on the CPU naturally.
+	 * So we save them into their _EL2 versions here.
+	 * For nVHE mode we trap accesses to those registers, so our
+	 * _EL2 copy in sys_regs[] is always up-to-date and we don't need
+	 * to save anything here.
+	 */
+	if (vcpu_el2_e2h_is_set(vcpu)) {
+		u64 val;
+
+		/*
+		 * We don't save CPTR_EL2, as accesses to CPACR_EL1
+		 * are always trapped, ensuring that the in-memory
+		 * copy is always up-to-date. A small blessing...
+		 */
+		__vcpu_sys_reg(vcpu, SCTLR_EL2)	= read_sysreg_el1(SYS_SCTLR);
+		__vcpu_sys_reg(vcpu, TTBR0_EL2)	= read_sysreg_el1(SYS_TTBR0);
+		__vcpu_sys_reg(vcpu, TTBR1_EL2)	= read_sysreg_el1(SYS_TTBR1);
+		__vcpu_sys_reg(vcpu, TCR_EL2)	= read_sysreg_el1(SYS_TCR);
+
+		if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
+			__vcpu_sys_reg(vcpu, TCR2_EL2) = read_sysreg_el1(SYS_TCR2);
+
+			if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
+				__vcpu_sys_reg(vcpu, PIRE0_EL2) = read_sysreg_el1(SYS_PIRE0);
+				__vcpu_sys_reg(vcpu, PIR_EL2) = read_sysreg_el1(SYS_PIR);
+			}
+
+			if (ctxt_has_s1poe(&vcpu->arch.ctxt))
+				__vcpu_sys_reg(vcpu, POR_EL2) = read_sysreg_el1(SYS_POR);
+		}
+
+		/*
+		 * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where
+		 * the interesting CNTHCTL_EL2 bits live. So preserve these
+		 * bits when reading back the guest-visible value.
+		 */
+		val = read_sysreg_el1(SYS_CNTKCTL);
+		val &= CNTKCTL_VALID_BITS;
+		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) &= ~CNTKCTL_VALID_BITS;
+		__vcpu_sys_reg(vcpu, CNTHCTL_EL2) |= val;
+	}
+
+	__vcpu_sys_reg(vcpu, SP_EL2)	= read_sysreg(sp_el1);
+	__vcpu_sys_reg(vcpu, ELR_EL2)	= read_sysreg_el1(SYS_ELR);
+	__vcpu_sys_reg(vcpu, SPSR_EL2)	= read_sysreg_el1(SYS_SPSR);
+}
+
+static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu)
+{
+	u64 val;
+
+	/* These registers are common with EL1 */
+	write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1),	par_el1);
+	write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1),	tpidr_el1);
+
+	write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt),			vpidr_el2);
+	write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1),			vmpidr_el2);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2),		SYS_MAIR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2),		SYS_VBAR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2),		SYS_CONTEXTIDR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2),		SYS_AMAIR);
+
+	if (vcpu_el2_e2h_is_set(vcpu)) {
+		/*
+		 * In VHE mode those registers are compatible between
+		 * EL1 and EL2.
+		 */
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2),   SYS_SCTLR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2),    SYS_CPACR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2),   SYS_TTBR0);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2),   SYS_TTBR1);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2),	    SYS_TCR);
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL);
+	} else {
+		/*
+		 * CNTHCTL_EL2 only affects EL1 when running nVHE, so
+		 * no need to restore it.
+		 */
+		val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2));
+		write_sysreg_el1(val, SYS_SCTLR);
+		val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2));
+		write_sysreg_el1(val, SYS_CPACR);
+		val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2));
+		write_sysreg_el1(val, SYS_TTBR0);
+		val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2));
+		write_sysreg_el1(val, SYS_TCR);
+	}
+
+	if (ctxt_has_tcrx(&vcpu->arch.ctxt)) {
+		write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2);
+
+		if (ctxt_has_s1pie(&vcpu->arch.ctxt)) {
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR);
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0);
+		}
+
+		if (ctxt_has_s1poe(&vcpu->arch.ctxt))
+			write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR);
+	}
+
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2),		SYS_ESR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2),	SYS_AFSR0);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2),	SYS_AFSR1);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2),		SYS_FAR);
+	write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2),		sp_el1);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2),		SYS_ELR);
+	write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2),	SYS_SPSR);
+}
+
 /*
  * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and
  * pstate, which are handled as part of the el2 return state) on every
@@ -66,8 +192,9 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
+	u64 midr, mpidr;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
 	__sysreg_save_user_state(host_ctxt);
 
 	/*
@@ -89,7 +216,24 @@ void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu)
 	 */
 	__sysreg32_restore_state(vcpu);
 	__sysreg_restore_user_state(guest_ctxt);
-	__sysreg_restore_el1_state(guest_ctxt);
+
+	if (unlikely(is_hyp_ctxt(vcpu))) {
+		__sysreg_restore_vel2_state(vcpu);
+	} else {
+		if (vcpu_has_nv(vcpu)) {
+			/*
+			 * As we're restoring a nested guest, set the value
+			 * provided by the guest hypervisor.
+			 */
+			midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2);
+			mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2);
+		} else {
+			midr = ctxt_midr_el1(guest_ctxt);
+			mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1);
+		}
+
+		__sysreg_restore_el1_state(guest_ctxt, midr, mpidr);
+	}
 
 	vcpu_set_flag(vcpu, SYSREGS_ON_CPU);
 }
@@ -110,9 +254,13 @@ void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt;
 	struct kvm_cpu_context *host_ctxt;
 
-	host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt;
+	host_ctxt = host_data_ptr(host_ctxt);
+
+	if (unlikely(is_hyp_ctxt(vcpu)))
+		__sysreg_save_vel2_state(vcpu);
+	else
+		__sysreg_save_el1_state(guest_ctxt);
 
-	__sysreg_save_el1_state(guest_ctxt);
 	__sysreg_save_user_state(guest_ctxt);
 	__sysreg32_save_state(vcpu);
 
diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c
index 1a60b95381e8..ec2569818629 100644
--- a/arch/arm64/kvm/hyp/vhe/tlb.c
+++ b/arch/arm64/kvm/hyp/vhe/tlb.c
@@ -17,8 +17,8 @@ struct tlb_inv_context {
 	u64			sctlr;
 };
 
-static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
-				  struct tlb_inv_context *cxt)
+static void enter_vmid_context(struct kvm_s2_mmu *mmu,
+			       struct tlb_inv_context *cxt)
 {
 	struct kvm_vcpu *vcpu = kvm_get_running_vcpu();
 	u64 val;
@@ -63,17 +63,17 @@ static void __tlb_switch_to_guest(struct kvm_s2_mmu *mmu,
 	__load_stage2(mmu, mmu->arch);
 	val = read_sysreg(hcr_el2);
 	val &= ~HCR_TGE;
-	write_sysreg(val, hcr_el2);
+	write_sysreg_hcr(val);
 	isb();
 }
 
-static void __tlb_switch_to_host(struct tlb_inv_context *cxt)
+static void exit_vmid_context(struct tlb_inv_context *cxt)
 {
 	/*
 	 * We're done with the TLB operation, let's restore the host's
 	 * view of HCR_EL2.
 	 */
-	write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2);
+	write_sysreg_hcr(HCR_HOST_VHE_FLAGS);
 	isb();
 
 	/* ... and the stage-2 MMU context that we switched away from */
@@ -97,7 +97,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -118,7 +118,7 @@ void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
@@ -129,7 +129,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nshst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -150,7 +150,7 @@ void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu,
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
@@ -169,7 +169,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__flush_s2_tlb_range_op(ipas2e1is, start, pages, stride,
 				TLBI_TTL_UNKNOWN);
@@ -179,7 +179,7 @@ void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu,
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
@@ -189,13 +189,13 @@ void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu)
 	dsb(ishst);
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
@@ -203,14 +203,14 @@ void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest(mmu, &cxt);
+	enter_vmid_context(mmu, &cxt);
 
 	__tlbi(vmalle1);
 	asm volatile("ic iallu");
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host(&cxt);
+	exit_vmid_context(&cxt);
 }
 
 void __kvm_flush_vm_context(void)
@@ -219,3 +219,150 @@ void __kvm_flush_vm_context(void)
 	__tlbi(alle1is);
 	dsb(ish);
 }
+
+/*
+ * TLB invalidation emulation for NV. For any given instruction, we
+ * perform the following transformtions:
+ *
+ * - a TLBI targeting EL2 S1 is remapped to EL1 S1
+ * - a non-shareable TLBI is upgraded to being inner-shareable
+ * - an outer-shareable TLBI is also mapped to inner-shareable
+ * - an nXS TLBI is upgraded to XS
+ */
+int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding)
+{
+	struct tlb_inv_context cxt;
+	int ret = 0;
+
+	/*
+	 * The guest will have provided its own DSB ISHST before trapping.
+	 * If it hasn't, that's its own problem, and we won't paper over it
+	 * (plus, there is plenty of extra synchronisation before we even
+	 * get here...).
+	 */
+
+	if (mmu)
+		enter_vmid_context(mmu, &cxt);
+
+	switch (sys_encoding) {
+	case OP_TLBI_ALLE2:
+	case OP_TLBI_ALLE2IS:
+	case OP_TLBI_ALLE2OS:
+	case OP_TLBI_VMALLE1:
+	case OP_TLBI_VMALLE1IS:
+	case OP_TLBI_VMALLE1OS:
+	case OP_TLBI_ALLE2NXS:
+	case OP_TLBI_ALLE2ISNXS:
+	case OP_TLBI_ALLE2OSNXS:
+	case OP_TLBI_VMALLE1NXS:
+	case OP_TLBI_VMALLE1ISNXS:
+	case OP_TLBI_VMALLE1OSNXS:
+		__tlbi(vmalle1is);
+		break;
+	case OP_TLBI_VAE2:
+	case OP_TLBI_VAE2IS:
+	case OP_TLBI_VAE2OS:
+	case OP_TLBI_VAE1:
+	case OP_TLBI_VAE1IS:
+	case OP_TLBI_VAE1OS:
+	case OP_TLBI_VAE2NXS:
+	case OP_TLBI_VAE2ISNXS:
+	case OP_TLBI_VAE2OSNXS:
+	case OP_TLBI_VAE1NXS:
+	case OP_TLBI_VAE1ISNXS:
+	case OP_TLBI_VAE1OSNXS:
+		__tlbi(vae1is, va);
+		break;
+	case OP_TLBI_VALE2:
+	case OP_TLBI_VALE2IS:
+	case OP_TLBI_VALE2OS:
+	case OP_TLBI_VALE1:
+	case OP_TLBI_VALE1IS:
+	case OP_TLBI_VALE1OS:
+	case OP_TLBI_VALE2NXS:
+	case OP_TLBI_VALE2ISNXS:
+	case OP_TLBI_VALE2OSNXS:
+	case OP_TLBI_VALE1NXS:
+	case OP_TLBI_VALE1ISNXS:
+	case OP_TLBI_VALE1OSNXS:
+		__tlbi(vale1is, va);
+		break;
+	case OP_TLBI_ASIDE1:
+	case OP_TLBI_ASIDE1IS:
+	case OP_TLBI_ASIDE1OS:
+	case OP_TLBI_ASIDE1NXS:
+	case OP_TLBI_ASIDE1ISNXS:
+	case OP_TLBI_ASIDE1OSNXS:
+		__tlbi(aside1is, va);
+		break;
+	case OP_TLBI_VAAE1:
+	case OP_TLBI_VAAE1IS:
+	case OP_TLBI_VAAE1OS:
+	case OP_TLBI_VAAE1NXS:
+	case OP_TLBI_VAAE1ISNXS:
+	case OP_TLBI_VAAE1OSNXS:
+		__tlbi(vaae1is, va);
+		break;
+	case OP_TLBI_VAALE1:
+	case OP_TLBI_VAALE1IS:
+	case OP_TLBI_VAALE1OS:
+	case OP_TLBI_VAALE1NXS:
+	case OP_TLBI_VAALE1ISNXS:
+	case OP_TLBI_VAALE1OSNXS:
+		__tlbi(vaale1is, va);
+		break;
+	case OP_TLBI_RVAE2:
+	case OP_TLBI_RVAE2IS:
+	case OP_TLBI_RVAE2OS:
+	case OP_TLBI_RVAE1:
+	case OP_TLBI_RVAE1IS:
+	case OP_TLBI_RVAE1OS:
+	case OP_TLBI_RVAE2NXS:
+	case OP_TLBI_RVAE2ISNXS:
+	case OP_TLBI_RVAE2OSNXS:
+	case OP_TLBI_RVAE1NXS:
+	case OP_TLBI_RVAE1ISNXS:
+	case OP_TLBI_RVAE1OSNXS:
+		__tlbi(rvae1is, va);
+		break;
+	case OP_TLBI_RVALE2:
+	case OP_TLBI_RVALE2IS:
+	case OP_TLBI_RVALE2OS:
+	case OP_TLBI_RVALE1:
+	case OP_TLBI_RVALE1IS:
+	case OP_TLBI_RVALE1OS:
+	case OP_TLBI_RVALE2NXS:
+	case OP_TLBI_RVALE2ISNXS:
+	case OP_TLBI_RVALE2OSNXS:
+	case OP_TLBI_RVALE1NXS:
+	case OP_TLBI_RVALE1ISNXS:
+	case OP_TLBI_RVALE1OSNXS:
+		__tlbi(rvale1is, va);
+		break;
+	case OP_TLBI_RVAAE1:
+	case OP_TLBI_RVAAE1IS:
+	case OP_TLBI_RVAAE1OS:
+	case OP_TLBI_RVAAE1NXS:
+	case OP_TLBI_RVAAE1ISNXS:
+	case OP_TLBI_RVAAE1OSNXS:
+		__tlbi(rvaae1is, va);
+		break;
+	case OP_TLBI_RVAALE1:
+	case OP_TLBI_RVAALE1IS:
+	case OP_TLBI_RVAALE1OS:
+	case OP_TLBI_RVAALE1NXS:
+	case OP_TLBI_RVAALE1ISNXS:
+	case OP_TLBI_RVAALE1OSNXS:
+		__tlbi(rvaale1is, va);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+	dsb(ish);
+	isb();
+
+	if (mmu)
+		exit_vmid_context(&cxt);
+
+	return ret;
+}